© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 124779
    Prev
    Next
    INDEX
    Explanations

    XML and DTD files

    np_max-act · gemini-2.0-flash

    This neuron detects XML/DTD entity declarations or parameter‐entity references (e.g. ENTITY, DTD, internal‐subset syntax).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insol
    -0.07
    [::-
    -0.07
    .canvas
    -0.06
     line
    -0.06
    Counter
    -0.06
     faster
    -0.06
     neighbor
    -0.06
    Line
    -0.06
     Newsletter
    -0.06
     Counter
    -0.06
    POSITIVE LOGITS
     pł
    0.07
    lv
    0.07
    $post
    0.07
     swirling
    0.06
     fray
    0.06
    tg
    0.06
    ético
    0.06
    aremos
    0.06
    یکی
    0.06
    pour
    0.06
    Activations Density 0.002%

    No Known Activations